Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4002 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0780. Min Range: -4.0780
Max Act: 4.0780. Min Act: -0.1700
Data Index: 6063237 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.9843. Min Act: -0.1700
Data Index: 6377069 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.9217. Min Act: -0.1700
Data Index: 1258905 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.7498. Min Act: -0.1700
Data Index: 5471869 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.7341. Min Act: -0.1700
Data Index: 2497355 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.7498. Min Act: -0.1700
Data Index: 6651475 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.7185. Min Act: -0.1700
Data Index: 2334217 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.7185. Min Act: -0.1700
Data Index: 4645965 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.6872. Min Act: -0.1700
Data Index: 408574 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.6715. Min Act: -0.1700
Data Index: 2795512 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.6559. Min Act: -0.1700
Data Index: 6395338 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.6402. Min Act: -0.1700
Data Index: 6373771 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.6559. Min Act: -0.1700
Data Index: 225393 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.6246. Min Act: -0.1700
Data Index: 614412 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.6246. Min Act: -0.1700
Data Index: 587699 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.6090. Min Act: -0.1700
Data Index: 6285456 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.5620. Min Act: -0.1700
Data Index: 6662911 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.5933. Min Act: -0.1700
Data Index: 5880263 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.6090. Min Act: -0.1700
Data Index: 4496405 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0780. Min Range: -4.0780
Max Act: 3.5620. Min Act: -0.1700
Data Index: 4044057 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19